| CPC G16H 50/20 (2018.01) [A61B 5/14503 (2013.01); A61B 5/14532 (2013.01); G06N 20/00 (2019.01); G16H 10/20 (2018.01); G16H 10/60 (2018.01); G16H 20/00 (2018.01); G16H 20/10 (2018.01); G16H 20/60 (2018.01); G16H 40/67 (2018.01)] | 3 Claims |
|
1. A computer-implemented method for managing blood glucose levels of a user, the method comprising:
causing a continuous glucose monitoring device comprising a subcutaneous sensor, in the user, to provide blood glucose values of the user, wherein the continuous glucose monitoring device is configured to continuously communicate with a server of an electronic device of the user via a Bluetooth protocol;
electronically receiving, at the server, using one or more processors, before generation of a treatment plan, initial data of the user including the blood glucose values of the user, a length of time that the user has been diagnosed with a blood glucose condition, types of medication to be consumed by the user, initial dosage of medication consumed by the user, historical A1C values of the user, and user health values, wherein the user health values are automatically retrieved from the electronic device and comprise heart rate, blood glucose, blood oxygen, blood pressure, activity, stress, mood, calories burned, and steps walked, wherein the calories burned and steps walked values are received from an application on the electronic device associated with a fitness band tracker, wherein the blood glucose values of the user are determined by automatically conducting a blood glucose test via a blood glucose test device coupled to the user, wherein health values retrieved from the electronic device may be retrieved based on a continuous transmission of the health values from a memory of the electronic device to the server;
storing, using the one or more processors, in a database connected to the one or more processors, the data received at the server;
encrypting the database to comply with at least one of a Health Insurance Portability and Accountability Act (HIPAA) privacy regulation, a healthcare regulation, a financial regulation, or a legal regulation;
extracting health data, using the one or more processors, from the stored data, the health data comprising cohort data comprising blood glucose values of one or more other users, wherein the cohort data is generated based on one or more individuals that match a demographic of the user and have one or more similarities with the user, the one or more similarities comprising a physical condition, a medical condition, and a psycho-determinant condition, wherein the demographic is one or more of an ethnicity, a gender, an age range, a height, and a weight;
inputting, using the one or more processors, the health data into one or more machine learning algorithms to generate the treatment plan for improving the blood glucose values of the user at an end of a treatment period, as compared to blood glucose values of the user at a beginning of the treatment period, the treatment plan for the user to achieve a goal based on the initial data of the user, wherein the treatment plan is based at least on the cohort data, wherein the cohort data is based on one or more individuals each having a successful treatment plan for a medical condition shared by the user and the one or more individuals, wherein the treatment plan is based on the length of time that the user has been diagnosed with the blood glucose condition, wherein a pre-determined delay is automatically applied between receiving the initial data and generating the treatment plan wherein the treatment plan includes instructions for tasks to be performed by the user during a first subset of the treatment period, wherein the tasks include one or more of prescribed blood glucose measurement pairs to be measured before and after meals, prescribed timing and medication to be consumed by the user, a prescribed amount of carbohydrates to be consumed by the user, or prescribed exercise for the user to perform, wherein the one or more machine learning algorithms include one or more of artificial neural networks, Bayesian statistics, case-based reason, decision trees, inductive logic processing, Gaussian process regression, Gene expression programming, Logistic model trees, stochastic modeling, or statistical modeling;
outputting the treatment plan for presentation on a graphical user interface (GUI) on the electronic device;
applying, using the one or more processors, the one or more machine learning algorithms to the data relating to the treatment plan to determine a medication compliance by comparing types, timing, and medication to prescribed types, timing, and medication, to determine a diet compliance by comparing a received amount of carbohydrates consumed to the prescribed amount of carbohydrates to be consumed, and to determine an exercise compliance by comparing the received amount of exercise performed to the prescribed amount of exercise to be performed;
applying, using the one or more processors, the one or more machine learning algorithms to the data relating to the treatment plan to analyze types, timing, and medications consumed by the user, amounts of carbohydrates consumed by the user, amount and quality of sleep of the user, the amount of exercise performed by the user, and the blood glucose levels of the user to identify patterns between the types, timing, and medications consumed by the user, the amounts of carbohydrates consumed by the user, the amount and quality of sleep of the user, the amount of exercise performed by the user, and the blood glucose levels of the user;
verifying access rights of the electronic device of the user, wherein the verifying comprises compliance with at least one of the Health Insurance Portability and Accountability Act (HIPAA) privacy regulation, the legal regulation, the healthcare regulation, a user account, as an intended device, or the financial regulation;
measuring user health values, via the electronic device of the user, the user health values including heart rate, blood glucose, blood oxygen, blood pressure, activity, stress, mood, and sleep;
disabling certain features of the electronic device, using the one or more processors, until the blood glucose levels of the user measured by the blood glucose test device are out of a hypoglycemic range;
generating, using the one or more processors, by an insulin titration machine learning algorithm, an insulin titration plan to optimize an insulin dosage of the user, the insulin titration plan including a starting dosage amount of insulin that is increased or decreased by an increment after a set period of time, a start date for the user to begin the insulin titration plan, requirements for the user to test the blood glucose levels at specific times of day, instructions for the user to use a specific type of insulin for treatment, a basal insulin regimen requiring one blood glucose measurement daily for three days to titrate the insulin dosage, and a bolus insulin regimen requiring one blood glucose measurement immediately after each meal at which insulin is dosed, wherein the insulin titration machine learning algorithm includes a basal insulin titration machine learning algorithm that determines the basal insulin regimen and a bolus insulin titration machine learning algorithm that determines the bolus insulin regimen;
increasing or decreasing, using the one or more processors, by the one or more machine learning algorithms, the increment based on blood glucose test results of the user;
sending a provider notification to a healthcare provider of the user via electronic messaging, using the one or more processors, via an electronic device of the healthcare provider, to alert the healthcare provider of the blood glucose test results of the user;
sending an insulin dosage notification to the user, using the one or more processors, via the electronic device of the user, the insulin dosage notification including directions to adjust the insulin dosage or to stop incrementing the insulin dosage, wherein the directions are output by the one or more machine learning algorithms;
outputting the treatment plan including the insulin dosage and the user health values, using the one or more processors, to the user via the electronic device of the user;
electronically receiving, using the one or more processors, data relating to the treatment plan during the first subset of the treatment period, the data relating to the treatment plan including types, timing, and dosages of medications consumed by the user, times and amounts of carbohydrates consumed by the user, amount of sleep of the user, amount of exercise performed by the user, and the blood glucose levels of the user;
receiving, using the one or more processors, global positioning system (GPS) data from the electronic device of the user;
receiving, using the one or more processors, weather data from the electronic device of the user, the weather data including weather conditions, current events, a current date, and a current season;
receiving, using the one or more processors, sleep data from the electronic device of the user, the sleep data including sleep duration and sleep quality based on measurements of light sleep, medium sleep, heavy sleep, and REM sleep;
identifying, using the one or more processors, and based on the received GPS data and a time proximity to one or more scheduled meals of the treatment plan to be consumed by the user, restaurants in proximity to the user and that are cataloged in a database, wherein the restaurant database includes meals offered by the cataloged restaurants and a carbohydrate content of each meal;
outputting a list of the identified restaurants, using the one or more processors, to the electronic device of the user, wherein the list includes recommended meals, of the meals offered at the identified restaurants, based on the carbohydrate content of the meals offered by the identified restaurants;
receiving, using the one or more processors, a selection of a catalogued restaurant, of the output list of the identified restaurants, from the user;
generating, using the one or more processors, a walking route for the user to travel along from a current location of the user to the selected restaurant;
receiving an indication from the user for the user to exercise, and, after receiving the indication from the user, retrieving GPS data from the electronic device of the user, and generating a route for the user to walk along, wherein a distance of the route corresponds to the prescribed exercise to the user in the treatment plan, wherein the weather data and the sleep data are used to generate the prescribed exercise;
revising the treatment plan, using the one or more processors, for a subsequent subset of the treatment period based on the diet compliance, the exercise compliance, the medication compliance, and the identified patterns;
outputting the revised treatment plan to the user, using the one or more processors, via the electronic device of the user, wherein the revised treatment plan includes one or more tasks to be performed by the user during the subsequent subset of the treatment period, wherein the tasks include a change in the one or more of the prescribed blood glucose measurement pairs to be measured before and after meals, the prescribed timing and medication to be consumed by the user, the prescribed amount of carbohydrates for the user to consume, or the prescribed exercise for the user to perform, as compared to the first subset of the treatment period;
outputting a report each week to the user, using the one or more processors, via the electronic device of the user, the report including meal logging activity, sleep activity, and blood sugar levels;
determining, using the one or more processors, based on the identified patterns, a trigger event that occurs before an adverse effect;
determining, using the one or more processors, a trend of the blood glucose values and a range for an upcoming blood glucose value based on the trend and a bolus insulin delivery time;
calculating, by the basal insulin titration machine learning algorithm, a timing and a dosing amount of basal insulin of the basal insulin regimen for the user at regular intervals;
administering, via an injection, in response to an output of the basal insulin titration machine learning algorithm, at the timing of basal insulin at the regular intervals, the dosing amount of basal insulin to the user;
calculating, by the bolus insulin titration machine learning algorithm, a dosing amount of bolus insulin of the bolus insulin regimen for the user, the bolus insulin delivery time corresponding to mealtimes;
administering, via an injection, in response to an output of the bolus insulin titration machine learning algorithm, at the bolus insulin delivery time at the mealtimes, the dosing amount of bolus insulin to the user;
synchronizing administration, in response to an output of the insulin titration machine learning algorithm, at the timing and the bolus insulin delivery time, of the dosing amount of basal insulin and the dosing amount of bolus insulin to the user;
outputting, using the one or more processors, via the electronic device of the user, the trend of the blood glucose values and the range for the upcoming blood glucose value;
sending a notification to the user, using the one or more processors, via the electronic device of the user, upon detecting an instance of the trigger event and based on the timing and the dosing amount of basal insulin and the bolus insulin delivery time and the dosing amount of bolus insulin, wherein the notification includes an identification of the trigger event to the user and an identification of the adverse effect; and
adjusting the user's insulin dosage based on upcoming blood glucose values of the user.
|